Enhancing fetal alcohol spectrum disorders diagnosis with a classifier based on the intracerebellar gradient of volumetric undersizing.

In fetal alcohol spectrum disorders (FASD), brain growth deficiency is a hallmark of subjects both with fetal alcohol syndrome (FAS) and with non-syndromic FASD (NS-FASD, i.e., those without specific diagnostic features). However, although the cerebellum was suggested to be more severely undersized than the rest of the brain, it has not yet been given a specific place in the FASD diagnostic criteria where neuroanatomical features still count for little if anything in diagnostic specificity. We applied a combination of cerebellar segmentation tools on a 1.5 T 3DT1 brain MRI dataset from a monocentric population of 89 FASD (52 FAS, 37 NS-FASD) and 126 typically developing controls (6-20 years old), providing 8 volumes: cerebellum, vermis and 3 lobes (anterior, posterior, inferior), plus total brain volume. After adjustment of confounders, the allometric scaling relationship between these cerebellar volumes (Vi ) and the total brain or cerebellum volume (Vt ) was fitted (Vi = bVt a ), and the effect of group (FAS, control) on allometric scaling was evaluated. We then estimated for each cerebellar volume in the FAS population the deviation from the typical scaling (v DTS) learned in the controls. Lastly, we trained and tested two classifiers to discriminate FAS from controls, one based on the total cerebellum v DTS only, the other based on all the cerebellar v DTS, comparing their performance both in the FAS and the NS-FASD group. Allometric scaling was significantly different between FAS and control group for all the cerebellar volumes (p < .001). We confirmed the excess of total cerebellum volume deficit (v DTS = -10.6%) and revealed an antero-inferior-posterior gradient of volumetric undersizing in the hemispheres (-12.4%, 1.1%, 2.0%, respectively) and the vermis (-16.7%, -9.2%, -8.6%, repectively). The classifier based on the intracerebellar gradient of v DTS performed more efficiently than the one based on total cerebellum v DTS only (AUC = 92% vs. 82%, p = .001). Setting a high probability threshold for >95% specificity of the classifiers, the gradient-based classifier identified 35% of the NS-FASD to have a FAS cerebellar phenotype, compared to 11% with the cerebellum-only classifier (pFISHER = 0.027). In a large series of FASD, this study details the volumetric undersizing within the cerebellum at the lobar and vermian level using allometric scaling, revealing an anterior-inferior-posterior gradient of vulnerability to prenatal alcohol exposure. It also strongly suggests that this intracerebellar gradient of volumetric undersizing may be a reliable neuroanatomical signature of FAS that could be used to improve the specificity of the diagnosis of NS-FASD.

The evaluation of cerebellum gross morphometric measurements in subjects having migraine, ataxia, dementia and vertigo / Evaluación de las medidas morfométricas macroscópicas del cerebelo en sujetos con migraña, ataxia, demencia, vértigo

SUMMARY: This paper was aimed to determine the morphometric measurements of cerebellum using MRI in subjects having migraine, ataxia, dementia and vertigo. Three hundred twenty six (326 subjects; 80 migraine subjects; 85 vertigo subjects; 83 dementia subjects; 78 ataxia subjects) subjects ranging from 20 up to 85 years were included in this study. Cerebellum morphometric measurements were taken from subjects having brain MRI in the Radiology Department. The means and standard deviations of the measurements were: Sagittal section cerebellum superior inferior length, 56.21±5.16 mm; sagittal section cerebellum anteroposterior length, 86.36 ±5.36 mm; axial section cerebellum antereoposterior length, 66.53±5.41 mm; axial section bi-cerebellar length, 100.48±5.14 mm; coronal section cerebellum supero-inferior length,53.60±3.84 mm; coronal section bi-cerebellar length, 99.77±6.24 mm in subjects with migraine, whereas the corresponding values were 62.33±8.66 mm; 93.31±9.89 mm; 60.26±7.98 mm; 99.89±6.41 mm; 54.35±4.64 mm; 85.58±14.74 mm in subjects with vertigo, respectively. The same values were found as 58.82±8.34 mm; 86.74±13.22 mm; 58.93±8.89 mm; 97.93±6.07 mm; 50.66±4.92 mm; 84.96±14.93 mm in patients having dementia, respectively, while the same measurements were as 60.83±8.59 mm; 92.18±9.12 mm; 57.76±7.85 mm; 97.71±5.82 mm; 52.48±4.85 mm; 81.49±14.38 mm in ataxia patients, respectively. Also, ages were divided into seven groups as decades. There were found significant difference in all parameters according to sex and ages (p<0.05). The cerebellum morphometry provides important and useful knowledge in terms of comparison of abnormalities clinicians and data will be valuable for the determination of pathologies for clinical disciplines.

RESUMEN: Este trabajo tuvo como objetivo determinar las medidas morfométricas del cerebelo mediante resonancia magnética en sujetos con migraña, ataxia, demencia y vértigo. Trescientos veintiseis sujetos (80 con migraña; 85 con vértigo; 83 con demencia y 78 con ataxia) entre los 20 y los 85 años de edad se incluyeron en este estudio. Se tomaron medidas morfométricas del cerebelo de sujetos sometidos a resonancia magnética en el Departamento de Radiología. Las medias y desviaciones estándar de las medidas fueron: sección sagital longitud superoinferior del cerebelo, 56,21±5,16 mm; sección sagital longitud anteroposterior del cerebelo, 86,36 ±5,36 mm; sección axial longitud anteroposterior del cerebelo, 66,53±5,41 mm; sección axial longitud bicerebelosa, 100,48±5,14 mm; sección coronal longitud superoinferior del cerebelo, 53,60±3,84 mm; longitud bicerebelosa de la sección coronal, 99,77±6,24 mm en sujetos con migraña, mientras que los valores correspondientes fueron 62,33±8,66 mm; 93,31±9,89mm; 60,26±7,98 mm; 99,89±6,41 mm; 54,35±4,64 mm; 85,58±14,74 mm en sujetos con vértigo, respectivamente. Se encontraron los mismos valores para pacientes con demencia 58,82±8,34 mm; 86,74±13,22 mm; 58,93±8,89 mm; 97,93±6,07 mm; 50,66±4,92 mm; 84,96±14,93 mm , respectivamente, mientras que las mismas medidas fueron de 60,83±8,59 mm; 92,18±9,12 mm; 57,76±7,85 mm; 97,71±5,82 mm; 52,48±4,85 mm; 81,49±14,38 mm en pacientes con ataxia, respectivamente. Las edades se dividieron en siete grupos, cada uno en década. Se encontraron diferencias significativas en todos los parámetros según sexo y edad (p<0,05). La morfometría del cerebelo proporciona un conocimiento importante y útil en términos de comparación de anormalidades clínicas y los datos serán valiosos para la determinación de patologías para las disciplinas clínicas.